Imagen de Portada

MobileLLM-R1: Exploring the Limits of Sub-Billion Language Model Reasoners with Open Training Recipes

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhao, Changsheng, Chang, Ernie, Liu, Zechun, Chang, Chia-Jung, Wen, Wei, Lai, Chen, Cao, Sheng, Tian, Yuandong, Krishnamoorthi, Raghuraman, Shi, Yangyang, Chandra, Vikas
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases
por: Liu, Zechun, et al.
Publicado: (2024)

MobileLLM-Pro Technical Report
por: Huber, Patrick, et al.
Publicado: (2025)

MobileMoE: Scaling On-Device Mixture of Experts
por: Chen, Yanbei, et al.
Publicado: (2026)

MobileLLM-Flash: Latency-Guided On-Device LLM Design for Industry Scale Deployment
por: Huang, Hanxian, et al.
Publicado: (2026)

SpinQuant: LLM quantization with learned rotations
por: Liu, Zechun, et al.
Publicado: (2024)

Agent-as-a-Judge: Evaluate Agents with Agents
por: Zhuge, Mingchen, et al.
Publicado: (2024)

Self-Vocabularizing Training for Neural Machine Translation
por: Lin, Pin-Jie, et al.
Publicado: (2025)

Target-Aware Language Modeling via Granular Data Sampling
por: Chang, Ernie, et al.
Publicado: (2024)

ParetoQ: Improving Scaling Laws in Extremely Low-bit LLM Quantization
por: Liu, Zechun, et al.
Publicado: (2025)

dTRPO: Trajectory Reduction in Policy Optimization of Diffusion Large Language Models
por: Zhang, Wenxuan, et al.
Publicado: (2026)

Basis Selection: Low-Rank Decomposition of Pretrained Large Language Models for Target Applications
por: Li, Yang, et al.
Publicado: (2024)

Breaking Down Power Barriers in On-Device Streaming ASR: Insights and Solutions
por: Li, Yang, et al.
Publicado: (2024)

Scaling Parameter-Constrained Language Models with Quality Data
por: Chang, Ernie, et al.
Publicado: (2024)

WinQ: Accelerating Quantization-Aware Training of Language Models Around Saddle Points
por: Li, Dongyue, et al.
Publicado: (2026)

RPRA: Predicting an LLM-Judge for Efficient but Performant Inference
por: Ashley, Dylan R., et al.
Publicado: (2026)

VideoAuto-R1: Video Auto Reasoning via Thinking Once, Answering Twice
por: Liu, Shuming, et al.
Publicado: (2026)

Folding Attention: Memory and Power Optimization for On-Device Transformer-based Streaming Speech Recognition
por: Li, Yang, et al.
Publicado: (2023)

AutoMixer: Checkpoint Artifacts as Automatic Data Mixers
por: Chang, Ernie, et al.
Publicado: (2025)

Exploring Audio Hallucination in Egocentric Video Understanding
por: Seth, Ashish, et al.
Publicado: (2026)

Param$Δ$ for Direct Weight Mixing: Post-Train Large Language Model at Zero Cost
por: Cao, Sheng, et al.
Publicado: (2025)

PathFusion: Path-consistent Lidar-Camera Deep Feature Fusion
por: Wu, Lemeng, et al.
Publicado: (2022)

Mixture-of-Supernets: Improving Weight-Sharing Supernet Training with Architecture-Routed Mixture-of-Experts
por: Jawahar, Ganesh, et al.
Publicado: (2023)

Neural Computers
por: Zhuge, Mingchen, et al.
Publicado: (2026)

Efficient Track Anything
por: Xiong, Yunyang, et al.
Publicado: (2024)

DepthShrinker: A New Compression Paradigm Towards Boosting Real-Hardware Efficiency of Compact Neural Networks
por: Fu, Yonggan, et al.
Publicado: (2022)

SqueezeSAM: User friendly mobile interactive segmentation
por: Varadarajan, Balakrishnan, et al.
Publicado: (2023)

Llama Guard 3-1B-INT4: Compact and Efficient Safeguard for Human-AI Conversations
por: Fedorov, Igor, et al.
Publicado: (2024)

STEM: Scaling Transformers with Embedding Modules
por: Sadhukhan, Ranajoy, et al.
Publicado: (2026)

LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding
por: Shen, Xiaoqian, et al.
Publicado: (2024)

EgoAVU: Egocentric Audio-Visual Understanding
por: Seth, Ashish, et al.
Publicado: (2026)

Rethinking the Text-Vision Reasoning Imbalance in MLLMs through the Lens of Training Recipes
por: Yao, Guanyu, et al.
Publicado: (2025)

R-Sparse: Rank-Aware Activation Sparsity for Efficient LLM Inference
por: Zhang, Zhenyu, et al.
Publicado: (2025)

OpenThoughts: Data Recipes for Reasoning Models
por: Guha, Etash, et al.
Publicado: (2025)

Diversify, Don't Fine-Tune: Scaling Up Visual Recognition Training with Synthetic Images
por: Yu, Zhuoran, et al.
Publicado: (2023)

Resource Allocation for Stable LLM Training in Mobile Edge Computing
por: Liu, Chang, et al.
Publicado: (2024)

Consistency Training with Physical Constraints
por: Chang, Che-Chia, et al.
Publicado: (2025)

Small Vision-Language Models are Smart Compressors for Long Video Understanding
por: Fei, Junjie, et al.
Publicado: (2026)

Communication Efficient Distributed Training with Distributed Lion
por: Liu, Bo, et al.
Publicado: (2024)

Stabilizing Physics-Informed Consistency Models via Structure-Preserving Training
por: Chang, Che-Chia, et al.
Publicado: (2026)

Efficient Universal Perception Encoder
por: Zhu, Chenchen, et al.
Publicado: (2026)